{"title":"Auto-segmentation of Adult-Type Diffuse Gliomas: Comparison of Transfer Learning-Based Convolutional Neural Network Model vs. Radiologists","authors":"","doi":"10.1007/s10278-024-01044-7","DOIUrl":null,"url":null,"abstract":"<h3>Abstract</h3> <p>Segmentation of glioma is crucial for quantitative brain tumor assessment, to guide therapeutic research and clinical management, but very time-consuming. Fully automated tools for the segmentation of multi-sequence MRI are needed. We developed and pretrained a deep learning (DL) model using publicly available datasets A (<em>n</em> = 210) and B (<em>n</em> = 369) containing FLAIR, T2WI, and contrast-enhanced (CE)-T1WI. This was then fine-tuned with our institutional dataset (<em>n</em> = 197) containing ADC, T2WI, and CE-T1WI, manually annotated by radiologists, and split into training (<em>n</em> = 100) and testing (<em>n</em> = 97) sets. The Dice similarity coefficient (DSC) was used to compare model outputs and manual labels. A third independent radiologist assessed segmentation quality on a semi-quantitative 5-scale score. Differences in DSC between new and recurrent gliomas, and between uni or multifocal gliomas were analyzed using the Mann–Whitney test. Semi-quantitative analyses were compared using the chi-square test. We found that there was good agreement between segmentations from the fine-tuned DL model and ground truth manual segmentations (median DSC: 0.729, std-dev: 0.134). DSC was higher for newly diagnosed (0.807) than recurrent (0.698) (<em>p</em> < 0.001), and higher for unifocal (0.747) than multi-focal (0.613) cases (<em>p</em> = 0.001). Semi-quantitative scores of DL and manual segmentation were not significantly different (mean: 3.567 vs. 3.639; 93.8% vs. 97.9% scoring ≥ 3, <em>p</em> = 0.107). In conclusion, the proposed transfer learning DL performed similarly to human radiologists in glioma segmentation on both structural and ADC sequences. Further improvement in segmenting challenging postoperative and multifocal glioma cases is needed.</p>","PeriodicalId":50214,"journal":{"name":"Journal of Digital Imaging","volume":"72 1","pages":""},"PeriodicalIF":2.9000,"publicationDate":"2024-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Digital Imaging","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1007/s10278-024-01044-7","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING","Score":null,"Total":0}
引用次数: 0
Abstract
Segmentation of glioma is crucial for quantitative brain tumor assessment, to guide therapeutic research and clinical management, but very time-consuming. Fully automated tools for the segmentation of multi-sequence MRI are needed. We developed and pretrained a deep learning (DL) model using publicly available datasets A (n = 210) and B (n = 369) containing FLAIR, T2WI, and contrast-enhanced (CE)-T1WI. This was then fine-tuned with our institutional dataset (n = 197) containing ADC, T2WI, and CE-T1WI, manually annotated by radiologists, and split into training (n = 100) and testing (n = 97) sets. The Dice similarity coefficient (DSC) was used to compare model outputs and manual labels. A third independent radiologist assessed segmentation quality on a semi-quantitative 5-scale score. Differences in DSC between new and recurrent gliomas, and between uni or multifocal gliomas were analyzed using the Mann–Whitney test. Semi-quantitative analyses were compared using the chi-square test. We found that there was good agreement between segmentations from the fine-tuned DL model and ground truth manual segmentations (median DSC: 0.729, std-dev: 0.134). DSC was higher for newly diagnosed (0.807) than recurrent (0.698) (p < 0.001), and higher for unifocal (0.747) than multi-focal (0.613) cases (p = 0.001). Semi-quantitative scores of DL and manual segmentation were not significantly different (mean: 3.567 vs. 3.639; 93.8% vs. 97.9% scoring ≥ 3, p = 0.107). In conclusion, the proposed transfer learning DL performed similarly to human radiologists in glioma segmentation on both structural and ADC sequences. Further improvement in segmenting challenging postoperative and multifocal glioma cases is needed.
期刊介绍：
The Journal of Digital Imaging (JDI) is the official peer-reviewed journal of the Society for Imaging Informatics in Medicine (SIIM). JDI’s goal is to enhance the exchange of knowledge encompassed by the general topic of Imaging Informatics in Medicine such as research and practice in clinical, engineering, and information technologies and techniques in all medical imaging environments. JDI topics are of interest to researchers, developers, educators, physicians, and imaging informatics professionals.
Suggested Topics
PACS and component systems; imaging informatics for the enterprise; image-enabled electronic medical records; RIS and HIS; digital image acquisition; image processing; image data compression; 3D, visualization, and multimedia; speech recognition; computer-aided diagnosis; facilities design; imaging vocabularies and ontologies; Transforming the Radiological Interpretation Process (TRIP™); DICOM and other standards; workflow and process modeling and simulation; quality assurance; archive integrity and security; teleradiology; digital mammography; and radiological informatics education.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
